Using clustering algorithms to examine the association between working memory training trajectories and therapeutic outcomes among psychiatric and healthy populations.

Working memory (WM) training has gained interest due to its potential to enhance cognitive functioning and reduce symptoms of mental disorders. Nevertheless, inconsistent results suggest that individual differences may have an impact on training efficacy. This study examined whether individual differences in training performance can predict therapeutic outcomes of WM training, measured as changes in anxiety and depression symptoms in sub-clinical and healthy populations. The study also investigated the association between cognitive abilities at baseline and different training improvement trajectories. Ninety-six participants (50 females, mean age = 27.67, SD = 8.84) were trained using the same WM training task (duration ranged between 7 to 15 sessions). An algorithm was then used to cluster them based on their learning trajectories. We found three main WM training trajectories, which in turn were related to changes in anxiety symptoms following the training. Additionally, executive function abilities at baseline predicted training trajectories. These findings highlight the potential for using clustering algorithms to reveal the benefits of cognitive training to alleviate maladaptive psychological symptoms.

Personalized cognitive training: Protocol for individual-level meta-analysis implementing machine learning methods.

Accumulating evidence suggests that cognitive training may enhance well-being. Yet, mixed findings imply that individual differences and training characteristics may interact to moderate training efficacy. To investigate this possibility, the current paper describes a protocol for a data-driven individual-level meta-analysis study aimed at developing personalized cognitive training. To facilitate comprehensive analysis, this protocol proposes criteria for data search, selection and pre-processing along with the rationale for each decision. Twenty-two cognitive training datasets comprising 1544 participants were collected. The datasets incorporated diverse training methods, all aimed at improving well-being. These training regimes differed in training characteristics such as targeted domain (e.g., working memory, attentional bias, interpretation bias, inhibitory control) and training duration, while participants differed in diagnostic status, age and sex. The planned analyses incorporate machine learning algorithms designed to identify which individuals will be most responsive to cognitive training in general and to discern which methods may be a better fit for certain individuals.